From:   isaku.yamahata@intel.com
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Paolo Bonzini <pbonzini@redhat.com>, erdemaktas@google.com,
        Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>
Subject: [PATCH v12 010/106] KVM: TDX: Add place holder for TDX VM specific mem_enc_op ioctl
Date:   Mon, 27 Feb 2023 00:22:09 -0800
Message-Id: <4e6cea32d83276bb887c1e484cb8389fa5728df7.1677484918.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1677484918.git.isaku.yamahata@intel.com>
References: <cover.1677484918.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Isaku Yamahata <isaku.yamahata@intel.com>

Add a place holder function for TDX specific VM-scoped ioctl as mem_enc_op.
TDX specific sub-commands will be added to retrieve/pass TDX specific
parameters.  Make mem_enc_ioctl non-optional as it's not optional now.

KVM_MEMORY_ENCRYPT_OP was introduced for VM-scoped operations specific for
guest state-protected VM.  It defined subcommands for technology-specific
operations under KVM_MEMORY_ENCRYPT_OP.  Despite its name, the subcommands
are not limited to memory encryption, but various technology-specific
operations are defined.  It's natural to repurpose KVM_MEMORY_ENCRYPT_OP
for TDX specific operations and define subcommands.

TDX requires VM-scoped TDX-specific operations for device model, for
example, qemu.  Getting system-wide parameters, TDX-specific VM
initialization.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  2 +-
 arch/x86/kvm/vmx/main.c            |  9 +++++++++
 arch/x86/kvm/vmx/tdx.c             | 26 ++++++++++++++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h         |  4 ++++
 arch/x86/kvm/x86.c                 |  4 ----
 5 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index b46dcac078b2..58fbaa05fc8c 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -117,7 +117,7 @@ KVM_X86_OP(enter_smm)
 KVM_X86_OP(leave_smm)
 KVM_X86_OP(enable_smi_window)
 #endif
-KVM_X86_OP_OPTIONAL(dev_mem_enc_ioctl)
+KVM_X86_OP(dev_mem_enc_ioctl)
 KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
 KVM_X86_OP_OPTIONAL(mem_enc_register_region)
 KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 620742d98ed3..d90da9fd75bf 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -37,6 +37,14 @@ static int vt_vm_init(struct kvm *kvm)
 	return vmx_vm_init(kvm);
 }
 
+static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
+{
+	if (!is_td(kvm))
+		return -ENOTTY;
+
+	return tdx_vm_ioctl(kvm, argp);
+}
+
 #define VMX_REQUIRED_APICV_INHIBITS		       \
 (						       \
        BIT(APICV_INHIBIT_REASON_DISABLE)|	       \
@@ -190,6 +198,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 
 	.dev_mem_enc_ioctl = tdx_dev_ioctl,
+	.mem_enc_ioctl = vt_mem_enc_ioctl,
 };
 
 struct kvm_x86_init_ops vt_init_ops __initdata = {
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 7a42eee995f6..cfedb2592725 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -67,6 +67,32 @@ int tdx_dev_ioctl(void __user *argp)
 	return 0;
 }
 
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_tdx_cmd tdx_cmd;
+	int r;
+
+	if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd)))
+		return -EFAULT;
+	if (tdx_cmd.error || tdx_cmd.unused)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	switch (tdx_cmd.id) {
+	default:
+		r = -EINVAL;
+		goto out;
+	}
+
+	if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd)))
+		r = -EFAULT;
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
 static int __init tdx_module_setup(void)
 {
 	const struct tdsysinfo_struct *tdsysinfo;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 5dc3f0d11427..6598e16f8e9f 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -141,10 +141,14 @@ void vmx_setup_mce(struct kvm_vcpu *vcpu);
 int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops);
 bool tdx_is_vm_type_supported(unsigned long type);
 int tdx_dev_ioctl(void __user *argp);
+
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
 #else
 static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -ENOSYS; }
 static inline bool tdx_is_vm_type_supported(unsigned long type) { return false; }
 static inline int tdx_dev_ioctl(void __user *argp) { return -EOPNOTSUPP; };
+
+static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c7459bc8b315..3e00fb7863a8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6961,10 +6961,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		goto out;
 	}
 	case KVM_MEMORY_ENCRYPT_OP: {
-		r = -ENOTTY;
-		if (!kvm_x86_ops.mem_enc_ioctl)
-			goto out;
-
 		r = static_call(kvm_x86_mem_enc_ioctl)(kvm, argp);
 		break;
 	}
-- 
2.25.1